Abstract
In this paper, we study the problem of domain generalization for person re-identification (re-ID), which adopts training data from multiple domains to learn a re-ID model that can be directly deployed to unseen target domains without further fine-tuning. One promising idea is removing the subsets of features that are not beneficial to the generalization of models. This can be achieved by muting the subset features that correspond to high back-propagated gradients as these subsets are easy for the model to overfit. But this method ignores the interaction of multiple domains. Therefore, we propose a novel method to solve this problem by comparing the gradients from two different training schemes. One of the training schemes discriminates input data from their corresponding domain to obtain back-propagated temporary gradients in the intermediate features. At the same time, another scheme discriminates input data from all domains to obtain the temporary gradients. By comparing the temporary gradient between the two schemes, we can identify the domain-generalizable subset features from those domain-specific subset features. We thus mute them in the subsequent training process to enforce the model to learn domain-generalizable information and improve its generalization. Extensive experiments on four large-scale re-ID benchmarks have verified the effectiveness of our method. Code is available at https://github.com/Ssd111/LEDF.git.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Carlucci, F.M., Porzi, L., Caputo, B., Ricci, E., Bulo, S.R.: Autodial: automatic domain alignment layers. In: ICCV (2017)
Ding, C., Wang, K., Wang, P., Tao, D.: Multi-task learning with coarse priors for robust part-aware person re-identification. TPAMI (2020)
Fan, H., Zheng, L., Yan, C., Yang, Y.: Unsupervised person re-identification: clustering and fine-tuning. TOMM (2018)
Ge, Y., Chen, D., Li, H.: Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. In: ICLR (2020)
Ge, Y., Zhu, F., Chen, D., Zhao, R., et al.: Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. In: NIPS (2020)
Gong, X., Yao, Z., Li, X., Fan, Y., Luo, B., Fan, J., Lao, B.: LAG-Net: multi-granularity network for person re-identification via local attention system. TMM (2021)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. ar**v preprint ar**v:1703.07737 (2017)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR (2017)
Huang, J., Guan, D., **ao, A., Lu, S.: FSDR: frequency space domain randomization for domain generalization. In: CVPR (2021)
Huang, Z., Wang, H., **ng, E.P., Huang, D.: Self-challenging improves cross-domain generalization. In: ECCV (2020)
**, X., Lan, C., Zeng, W., Chen, Z.: Feature alignment and restoration for domain generalization and adaptation. ar**v preprint ar**v:2006.12009 (2020)
**, X., Lan, C., Zeng, W., Chen, Z., Zhang, L.: Style normalization and restitution for generalizable person re-identification. In: CVPR (2020)
Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Learning to generalize: meta-learning for domain generalization. In: AAAI (2018)
Li, H., Pan, S.J., Wang, S., Kot, A.C.: Domain generalization with adversarial feature learning. In: CVPR (2018)
Li, L., et al.: Progressive domain expansion network for single domain generalization. In: CVPR (2021)
Li, P., Li, D., Li, W., Gong, S., Fu, Y., Hospedales, T.M.: A simple feature augmentation for domain generalization. In: ICCV (2021)
Li, W., Wang, X.: Locally aligned feature transforms across views. In: CVPR (2013)
Li, W., Zhao, R., **ao, T., Wang, X.: Deepreid: deep filter pairing neural network for person re-identification. In: CVPR (2014)
Mahajan, D., Tople, S., Sharma, A.: Domain generalization using causal matching. In: ICML (2021)
Mansilla, L., Echeveste, R., Milone, D.H., Ferrante, E.: Domain generalization via gradient surgery. In: ICCV (2021)
Muandet, K., Balduzzi, D., Schölkopf, B.: Domain generalization via invariant feature representation. In: ICML (2013)
Pan, X., Luo, P., Shi, J., Tang, X.: Two at once: enhancing learning and generalization capacities via ibn-net. In: ECCV (2018)
Panareda Busto, P., Gall, J.: Open set domain adaptation. In: ICCV (2017)
Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: ECCV Workshop (2016)
Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR (2018)
Shi, Y., et al.: Gradient matching for domain generalization. In: ICLR (2022)
Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: ECCV (2018)
Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: CVPR (2018)
**ang, W., Huang, J., Hua, X.S., Zhang, L.: Part-aware attention network for person re-identification. In: ACCV (2020)
Yan, C., et al.: Beyond triplet loss: person re-identification with fine-grained difference-aware pairwise loss. TMM (2021)
Yang, F., et al.: Asymmetric co-teaching for unsupervised cross-domain person re-identification. In: AAAI (2020)
Yang, F., et al.: Learning to attack real-world models for person re-identification via virtual-guided meta-learning. In: AAAI (2021)
Yang, F., et al.: Joint noise-tolerant learning and meta camera shift adaptation for unsupervised person re-identification. In: CVPR (2021)
Ye, M., Shen, J., Lin, G., **ang, T., Shao, L., Hoi, S.C.: Deep learning for person re-identification: a survey and outlook. TPAMI (2021)
Yu, H.X., Zheng, W.S., Wu, A., Guo, X., Gong, S., Lai, J.H.: Unsupervised person re-identification by soft multilabel learning. In: CVPR (2019)
Zhang, Z., Lan, C., Zeng, W., **, X., Chen, Z.: Relation-aware global attention for person re-identification. In: CVPR (2020)
Zhao, Y., et al.: Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification. In: CVPR (2021)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV (2015)
Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV (2017)
Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: CVPR (2017)
Zhong, Z., Zheng, L., Luo, Z., Li, S., Yang, Y.: Invariance matters: exemplar memory for domain adaptive person re-identification. In: CVPR (2019)
Zhou, K., Yang, Y., Cavallaro, A., **ang, T.: Learning generalisable omni-scale representations for person re-identification. TPAMI (2021)
Zhou, K., Yang, Y., Hospedales, T., **ang, T.: Learning to generate novel domains for domain generalization. In: ECCV (2020)
Zhou, K., Yang, Y., Qiao, Y., **ang, T.: Domain generalization with mixstyle. In: ICLR (2021)
Zhu, Z., et al.: Aware loss with angular regularization for person re-identification. In: AAAI (2020)
Acknowledgement
This work is supported by the National Nature Science Foundation of China (No. 61876159, 62276221), the Natural Science Foundation of Fujian Province of China (No. 2022J01002), the Science and Technology Plan Project of **amen (No. 3502Z20221025).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, W., Yang, F., Luo, Z., Li, S. (2023). Generalized Person Re-identification by Locating and Eliminating Domain-Sensitive Features. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13846. Springer, Cham. https://doi.org/10.1007/978-3-031-26351-4_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-26351-4_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26350-7
Online ISBN: 978-3-031-26351-4
eBook Packages: Computer ScienceComputer Science (R0)